Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    operate
    -0.07
    word
    -0.07
    :key
    -0.06
     Browse
    -0.06
     документів
    -0.06
     browse
    -0.06
    :";↵
    -0.06
     consultants
    -0.06
     Пра
    -0.06
    olve
    -0.06
    POSITIVE LOGITS
    _ANY
    0.07
    ाहरण
    0.07
     ObjectMapper
    0.07
    .detach
    0.07
    .ACCESS
    0.07
     编
    0.06
     Loader
    0.06
     영향을
    0.06
    StorageSync
    0.06
     absolute
    0.06
    Act Density 0.004%

    No Known Activations